RelativePreferenceOptimization

書いてみる

関連タグ

#Adaptability (7)
#ContrastingResponses (1)
#LLMAlignment (1)
#データ (31,204)
#使用 (3,505)
#手法 (4,812)

Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts

Ikemen Mas Kot
6か月前